© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61886
    Prev
    Next
    INDEX
    Explanations

    word usage confusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸Ńิà¸ĩ
    -0.08
    RelativeTo
    -0.08
    .ParseException
    -0.08
    è£ħ饰设计
    -0.08
    亥
    -0.08
    toa
    -0.08
     Equals
    -0.08
     ($.
    -0.07
    æĶ¾äºĨ
    -0.07
    æijĴ
    -0.07
    POSITIVE LOGITS
    å¡«åħ¥
    0.09
    YS
    0.08
    å¤ĩéĢī
    0.07
    Fill
    0.07
    å¡«
    0.07
    填空
    0.07
    åIJĪéĢĤçļĦ
    0.06
     filling
    0.06
    ys
    0.06
    aken
    0.06
    Activations Density 0.003%

    No Known Activations